keras Regressor 回归

import numpy as np
np.random.seed(1337)  # for reproducibility
from keras.models import Sequential
from keras.layers import Dense
import matplotlib.pyplot as plt # 可视化模块

import tensorflow as tf
import keras.backend.tensorflow_backend as KTF

# create some data
N = 2000
X = np.linspace(-1, 1, N)
np.random.shuffle(X)    # randomize the data
Y = 0.5 * X + 2 + np.random.normal(0, 0.05, X.shape)*0.1
# plot data
plt.scatter(X, Y)
plt.show()

train_N = int(N*0.8)
X_train, Y_train = X[:train_N], Y[:train_N]     # train 前 160 data points
X_test, Y_test = X[train_N:], Y[train_N:]       # test 后 40 data points

model = Sequential()
model.add(Dense(output_dim=1, input_dim=1))

# choose loss function and optimizing method
model.compile(loss='mse', optimizer='sgd')

# training
print('Training -----------')
config = tf.ConfigProto()
config.gpu_options.allow_growth = True  # 不全部占满显存, 按需分配
config.gpu_options.per_process_gpu_memory_fraction = 0.8  #限制GPU内存占用率

init=tf.global_variables_initializer()
sess = tf.Session(config=config)
KTF.set_session(sess)  # 设置session

for step in range(2001):
    cost = model.train_on_batch(X_train, Y_train)
    if step % 200 == 0:
        print('train cost: ', cost)
        
# test
print('\nTesting ------------')
cost = model.evaluate(X_test, Y_test, batch_size=N-train_N)
print('test cost:', cost)
W, b = model.layers[0].get_weights()
print('Weights=', W, '\nbiases=', b)      

# plotting the prediction
Y_pred = model.predict(X_test)
plt.scatter(X_test, Y_test)
plt.plot(X_test, Y_pred)
plt.show()